Skip to content
#5 in Deep LearningUdemyDeep LearningPaid courseBeginner level

Artificial Neural Network for Regression (Udemy.com)

Build an ANN Regression model to predict the electrical energy output of a Combined Cycle Power Plant

Created by: Hadelin de Ponteves

Last updated June 2026

Our take

Based on the ratings of 6,511 students, a sample of their written reviews and the syllabus, as the course stood in June 2026. No course pays to be reviewed.

A free, 72 minute case study from Hadelin de Ponteves and the SuperDataScience team. You load a power plant dataset in Google Colab, build a small Keras network in TensorFlow 2, train it, and predict hourly energy output. Fourteen lectures across five sections, no quizzes or coding exercises. Udemy files it as beginner, but the requirements list deep learning basics, and reviewers agree: it works best as a follow-on to the same team's Deep Learning A-Z or Machine Learning A-Z, where the ANN theory is actually taught. On its own it is a demo of the workflow, not an explanation of it.

Students like the clarity. Reviewers call it very well explained, and one likes that Hadelin recaps definitions before adding anything new. The rating breakdown backs that up: over 6,000 of 6,500 reviews are four or five stars. The complaints are consistent. Four-star reviewers want to know why two hidden layers, how many neurons, what batch size and how many epochs, and the course never says. One reviewer points out there are no metrics to evaluate the model. A three-star review calls it a preview built to sell the paid courses, which is fair. One older two-star review hit a Keras error running the code, though the course was refreshed in June 2026.

Value is hard to argue with, since it costs nothing. It sits beside much longer paid courses in our Deep Learning list and is not a substitute for any of them. Treat it as a one-hour sample of Hadelin's teaching before paying for Deep Learning A-Z, or as a short regression exercise after finishing it. Anyone who wants exactly that should enroll and be done by lunch. Anyone hoping to learn how to tune a network should keep looking.

Best forPeople partway through Deep Learning A-Z or Machine Learning A-Z who want one quick regression project to cement the ANN section.
Skip it ifYou want to learn why a network has a given number of layers, neurons or epochs. This course picks values and never explains them.

Pros

  • Free, and finishes in about an hour with a working regression model.
  • Reviewers say Hadelin recaps definitions before each new step and explains things very well.
  • Runs in Google Colab, so there is nothing to install.
  • Refreshed in June 2026, and 93 percent of 6,500 reviews are four or five stars.

Cons

  • Layer counts, neuron counts, batch size and epochs are chosen without explanation.
  • No metrics to evaluate the model, no quizzes, no exercises.
  • Really a preview of the paid Deep Learning A-Z course, and assumes you know ANN basics already.
A short and well-structured course, best suited if you’ve already completed the author’s detailed course. This project nicely complements the learning by demonstrating regression using ANN.
Vishal Saxena, a student

Listed as beginner, but the requirements say deep learning basics. Suits people who already know what an ANN is.

icon
What you will learn

  • How to implement an Artificial Neural Network in Python
  • How to do Regression
  • How to use Google Colab

Course content

5 sections · 14 lectures · 1.2 hours of video 4 articles

  1. 1Introduction 2 free previews5 lectures · 13 min
  2. 2Part 1 - Data Preprocessing2 lectures · 17 min
  3. 3Part 2 - Building the ANN3 lectures · 18 min
  4. 4Part 3 - Training the ANN3 lectures · 24 min
  5. 5Congratulations!! Don't forget your Prize :)1 lecture

Who it is for

The instructor says it suits

  • Anyone interested in Machine Learning and Deep Learning

What you need before you start

  • Deep Learning Basics

icon
Course Description

Are you ready to flex your Deep Learning skills by learning how to build and implement an Artificial Neural Network using Python from scratch?

Testing your skills with practical courses is one of the best and most enjoyable ways to learn data science…and now we’re giving you that chance for FREE.


In this free course, AI expert Hadelin de Ponteves guides you through a case study that shows you how to build an ANN Regression model to predict the electrical energy output of a Combined Cycle Power Plant.

The objective is to create a data model that predicts the net hourly electrical energy output (EP) of the plant using available hourly average ambient variables.

Go hands-on with Hadelin in solving this complex, real-world Deep Learning challenge that covers everything from data preprocessing to building and training an ANN, while utilizing the Machine Learning library, Tensorflow 2.0, and Google Colab, the free, browser-based notebook environment that runs completely in the cloud. It’s a game-changing interface that will supercharge your Machine Learning toolkit.


Check out what’s in store for you when you enroll:

Part 1: Data Preprocessing

  • Importing the dataset

  • Splitting the dataset into the training set and test set

Part 2: Building an ANN

  • Initializing the ANN

  • Adding the input layer and the first hidden layer

  • Adding the output layer

  • Compiling the ANN

Part 3: Training the ANN

  • Training the ANN model on the training set

  • Predicting the results of the test set


More about Combined-Cycle Power Plants

A combined-cycle power plant is an electrical power plant in which a Gas Turbine (GT) and a Steam Turbine (ST) are used in combination to produce more electrical energy from the same fuel than that would be possible from a single cycle power plant.

The gas turbine compresses air and mixes it with a fuel heated to a very high temperature. The hot air-fuel mixture moves through the blades, making them spin. The fast-spinning gas turbine drives a generator to generate electricity. The exhaust (waste) heat escaped through the exhaust stack of the gas turbine is utilized by a Heat Recovery Steam Generator (HSRG) system to produce steam that spins a steam turbine. This steam turbine drives a generator to produce additional electricity. CCCP is assumed to produce 50% more energy than a single power plant.


icon
Udemy Discount

The discount is applied through our link. Open the course from here and Udemy's current promotional price is applied at checkout on most courses, no code to type.

Some courses are excluded from Udemy's promotions. If the price does not drop, clear your browser cookies and use the button again.

icon
Instructor Details

Hadelin de Ponteves

Hadelin is one of Udemy’s top instructors and a recognized leader in AI education. He has taught AI to over 2.6 million learners worldwide and is a frequent guest speaker at prominent industry events. Hadelin has created more than 30 top-rated courses on topics such as AI, Machine Learning, Deep Learning, Blockchain, and Cloud Computing, empowering learners around the globe to upskill in cutting-edge technologies.

In addition to his partnership with Udemy, Hadelin is the co-founder of CloudWolf and SuperDataScience. He is passionate about education and is on a mission to make complex technologies simple, practical, and widely accessible to all.

As a side activity, he is also an actor who acted in seven films, and a movie producer of two films (Indian and French).

icon
More courses by Hadelin de Ponteves

$199.99

$159.99

$99.99

Free

$119.99

$89.99

icon
More Deep Learning courses

$109.99

$109.99

$79.99

$119.99

$124.99

$124.99

icon
Reviews

4.7

6,511 ratings on Udemy

Select a bar to show only those reviews.Select the bar again to show every rating.

By Manoj Kumar Beriya on 11/15/2023

It was a good learning experience, but I want to know how to select the number of hidden layers, the number of neurons in each layer, the learning rate, and the optimum size and how to optimize all these parameters.

By Thomas K. Carpenter on 7/14/2023

I am very excited to learn as much as I can about machine learning. The UCI Machine Learning Repository was a great find. I am glad that you introduced it, so that I can practice Classification, Regression, and other types of Neural Networks.

By Kenan FIRAT on 2/8/2023

I come here from Machine Learning Tutorial. Those guys really perfect. They do teachin a enjoying and friendly even also scientific manner. In this part Regression ANN just i have question so here is not Q&a Thats why I feel ask here . as I remember from Machine Learning it was highly advised to make feature scaling and here is we dont. I apply it by myself but i saw the predicted values are gotten very close as much as they are same. Do i miss something.

By Felipe Silveira Carvalho on 3/5/2021

I liked the course, It gives a good basic to start learning about ANN, you can see a real aplication in solving problems. I just think the quality of the image could be better, sometimes I have had difficulties in seeing what was writed. But, in general, the course gives what it promisses. Thanks.

By Purna Sati Chandrala on 2/8/2021

Well what can I say. It's an Awesome course and above expectations. I bought the Machine Learning A-Z course in 2019 but somehow never gone beyond first 4 videos. This course gave me a new nice feel and motivation to start that now and complete it soon. Thank You for making this course!! Love the way you explain with so much enthusiasm to teach and in a joyful tone!

By Guillaume D. Albert on 1/14/2021

This is a great hands-on course in the path to Deep Learning and AI mastery. It guides you step-by-step and with clear explanation through a simple (yet kinda complex) project. The teacher is clearly passionate. really knows his stuff and does an excellent job of explaining things in a language that even a novice can undestand. Overall, this is a great place to start and get to motivated for the next, longer/heavier courses ahead in the Machine Learning/Deep Learning path. And you get to actually complete a full project in less than an hour, which is awesome for moral :)

By Ray S on 11/12/2020

Great course to achieve the conceptual understanding of the Artificial Neural Network. The short duration of the course makes it exciting, especially for the beginners, without overwhelming them. Yet it delivers very good contents, explained fully (top-level ideas) in the simplest words possible, in a step by step manner. The instructor is very enthusiastic, which makes the course really engaging in its entirety. Ultimately, this course leaves you with just the right amount of motivation and inspiration to proceed forward in the journey of mastering the broader AI.

By Frederick Zhang on 9/30/2020

If you completed Section 3 (ANN Intuition) and Section 4 (Building an ANN) of the Deep Learning A-Z course, which taught you how to build and train an ANN for classification, you should breeze right through this course. It's good to have the theory in mind as you follow along with the instructor. Make sure to take notes in the Collab notebook for specific steps so not only do you know what you're doing but also why you're doing it.

By Ricardo Segura on 8/11/2020

Breve y claro! Se debe tener conocimientos previos para sacar el máximo provecho a este curso pero sin duda es muy útil y se complementa con el full course de pago! Estoy ansioso por saber y aprender más de este mundo del ML,DL y AI.

By Brian Hughes on 7/14/2020

This course was extremely helpful for me, as it directly applied to what I'm trying to do at work. Was able to follow it step-by-step with complete success. The instructor does a fantastic job explaining every step in an easy-to-understand manner.

Showing all 10 reviews on CourseDuck

Read all 6,511 reviews on Udemy

icon
Quality Score

No CourseDuck member has rated this course yet. Taken it? Give each part a thumbs up or down.

Content Quality
/
Video Quality
/
Qualified Instructor
/
Course Pace
/
Course Depth & Coverage
/

Overall Score : 94 / 100